SOTAVerified

3D Human Pose Estimation

3D Human Pose Estimation is a computer vision task that involves estimating the 3D positions and orientations of body joints and bones from 2D images or videos. The goal is to reconstruct the 3D pose of a person in real-time, which can be used in a variety of applications, such as virtual reality, human-computer interaction, and motion analysis.

Papers

Showing 601625 of 665 papers

TitleStatusHype
Ordinal Depth Supervision for 3D Human Pose EstimationCode0
OriNet: A Fully Convolutional Network for 3D Human Pose EstimationCode0
Integral Human Pose RegressionCode0
Human Mesh Recovery from Monocular Images via a Skeleton-disentangled RepresentationCode0
3D Human Pose Estimation with 2D Marginal HeatmapsCode0
XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB CameraCode0
HSTFormer: Hierarchical Spatial-Temporal Transformers for 3D Human Pose EstimationCode0
HPERL: 3D Human Pose Estimation from RGB and LiDARCode0
2D/3D Pose Estimation and Action Recognition using Multitask Deep LearningCode0
Compositional Human Pose RegressionCode0
How Robust is 3D Human Pose Estimation to Occlusion?Code0
Hierarchical Graph Networks for 3D Human Pose EstimationCode0
CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape EstimationCode0
Heuristic Weakly Supervised 3D Human Pose EstimationCode0
PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human DigitizationCode0
PLIKS: A Pseudo-Linear Inverse Kinematic Solver for 3D Human Body EstimationCode0
Chirality Nets for Human Pose RegressionCode0
Can WiFi Estimate Person Pose?Code0
FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformERCode0
HDiffTG: A Lightweight Hybrid Diffusion-Transformer-GCN Architecture for 3D Human Pose EstimationCode0
Learnable Triangulation of Human PoseCode0
Camera Motion Agnostic 3D Human Pose EstimationCode0
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density NetworkCode0
PoseGRAF: Geometric-Reinforced Adaptive Fusion for Monocular 3D Human Pose EstimationCode0
Vision-based Control of a Quadrotor in User Proximity: Mediated vs End-to-End Learning ApproachesCode0
Show:102550
← PrevPage 25 of 27Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Simple-baselinePA-MPJPE157Unverified
2HMRMPJPE130Unverified
3BMPMPVPE119.3Unverified
4SPINMPVPE116.4Unverified
5Wenshuo et a;.MPVPE112.6Unverified
6TCMR (T=16 w/o 3DPW)MPVPE111.5Unverified
7CHOMPMPVPE110.1Unverified
8PC-HMRMPVPE108.6Unverified
93DCrowdNetMPVPE108.5Unverified
10SMPLifyPA-MPJPE106.8Unverified
#ModelMetricClaimedVerifiedStatus
1VNect (Augm.)MPJPE124.7Unverified
2HMRMPJPE124.2Unverified
3Single-Shot Multi-PersonMPJPE122.2Unverified
4MehtaMPJPE117.6Unverified
5PONetMPJPE115Unverified
6Pose Consensus (monocular)MPJPE112.1Unverified
7GeoRep (fully-supervised)MPJPE110.8Unverified
8XFormer (HRNet)MPJPE109.8Unverified
9EpipolarPose (fully-supervised)MPJPE108.99Unverified
10SPINMPJPE105.2Unverified